{"id":"https://openalex.org/W2914926228","doi":"https://doi.org/10.1145/3293320.3293334","title":"Optimizing parallel GEMM routines using auto-tuning with Intel AVX-512","display_name":"Optimizing parallel GEMM routines using auto-tuning with Intel AVX-512","publication_year":2019,"publication_date":"2019-01-14","ids":{"openalex":"https://openalex.org/W2914926228","doi":"https://doi.org/10.1145/3293320.3293334","mag":"2914926228"},"language":"en","primary_location":{"id":"doi:10.1145/3293320.3293334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293320.3293334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101864145","display_name":"Raehyun Kim","orcid":"https://orcid.org/0000-0002-0053-0330"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Raehyun Kim","raw_affiliation_strings":["Soongsil University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Soongsil University, Seoul, Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044068522","display_name":"Jaeyoung Choi","orcid":"https://orcid.org/0000-0002-7321-9682"},"institutions":[{"id":"https://openalex.org/I141371507","display_name":"Soongsil University","ror":"https://ror.org/017xnm587","country_code":"KR","type":"education","lineage":["https://openalex.org/I141371507"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyoung Choi","raw_affiliation_strings":["Soongsil University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Soongsil University, Seoul, Korea","institution_ids":["https://openalex.org/I141371507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101699334","display_name":"Myungho Lee","orcid":"https://orcid.org/0000-0003-4383-6425"},"institutions":[{"id":"https://openalex.org/I89440247","display_name":"Myongji University","ror":"https://ror.org/00s9dpb54","country_code":"KR","type":"education","lineage":["https://openalex.org/I89440247"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myungho Lee","raw_affiliation_strings":["Myongji University, Yongin, Gyeonggi, Korea"],"affiliations":[{"raw_affiliation_string":"Myongji University, Yongin, Gyeonggi, Korea","institution_ids":["https://openalex.org/I89440247"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101864145"],"corresponding_institution_ids":["https://openalex.org/I141371507"],"apc_list":null,"apc_paid":null,"fwci":3.3707,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92486303,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.8794652819633484},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8497668504714966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7911289930343628},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5479561686515808},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5244622230529785},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.46960434317588806},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.4651418924331665},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4568506181240082},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45576155185699463},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4237663149833679},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4189842939376831},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23774287104606628},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.20303821563720703},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16209125518798828},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12306982278823853},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11433383822441101},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.11019536852836609},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.09232795238494873}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8794652819633484},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8497668504714966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7911289930343628},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5479561686515808},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5244622230529785},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.46960434317588806},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.4651418924331665},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4568506181240082},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45576155185699463},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4237663149833679},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4189842939376831},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23774287104606628},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.20303821563720703},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16209125518798828},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12306982278823853},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11433383822441101},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.11019536852836609},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.09232795238494873},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293320.3293334","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293320.3293334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1983157164","https://openalex.org/W2043275593","https://openalex.org/W2064872546","https://openalex.org/W2073061372","https://openalex.org/W2099059741","https://openalex.org/W2135653967","https://openalex.org/W2170996201","https://openalex.org/W2412152731","https://openalex.org/W2485412435","https://openalex.org/W2516525699","https://openalex.org/W2746871167","https://openalex.org/W2788448998","https://openalex.org/W2806900363","https://openalex.org/W2902243168","https://openalex.org/W4243796884","https://openalex.org/W4251235123"],"related_works":["https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121","https://openalex.org/W3033264647","https://openalex.org/W4214765606"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,16,26,37,47,50,58,67,90,95],"optimal":[4,63],"implementations":[5],"of":[6,69,83],"single-":[7],"and":[8,25,61,76,98],"double-precision":[9],"general":[10],"matrix-matrix":[11],"multiplication":[12],"(GEMM)":[13],"routines":[14],"for":[15],"Intel":[17,27,38,96],"Xeon":[18,28],"Phi":[19],"Processor":[20],"code-named":[21],"Knights":[22],"Landing":[23],"(KNL)":[24],"Scalable":[29],"Processors":[30],"based":[31],"on":[32],"an":[33],"auto-tuning":[34,43],"approach":[35,44,55],"with":[36],"AVX-512":[39],"intrinsic":[40],"functions.":[41],"Our":[42,54],"precisely":[45],"determines":[46],"parameters":[48],"reflecting":[49],"target":[51],"architectural":[52],"features.":[53],"significantly":[56],"reduces":[57],"search":[59],"space":[60],"derives":[62],"parameter":[64],"sets":[65],"including":[66],"size":[68],"submatrices,":[70],"prefetch":[71],"distances,":[72],"loop":[73],"unrolling":[74],"depth,":[75],"parallelization":[77],"scheme.":[78],"Without":[79],"a":[80],"single":[81],"line":[82],"assembly":[84],"code,":[85],"our":[86],"GEMM":[87],"kernels":[88],"show":[89],"comparable":[91],"performance":[92],"results":[93],"to":[94],"MKL":[97],"outperform":[99],"other":[100],"open-source":[101],"BLAS":[102],"libraries.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}